Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9a0ab401df892c7a345b88766e69f892cccc618c64656b4a3a99e894215f24
+oid sha256:ec6f9b2e70ccc732a35b6e378f107fdd5a9a3672117da6450ca0368dec14f08e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099cb6fb5e9a74ba8a95458effa35c9a2d02b76b8c31f1c26e02c67b177633ba
+oid sha256:76fc1276660a99fcaea1de155443d582606f30500bd6240611b76e06b21c9657
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffebe53bb7ba616f107698a0b1a02f06c6aa1d2c94c3d496fc7acc3a9916ac88
+oid sha256:113786fe81b4cc603fbc0388faa5bf86e33a11a5456e3cb2350330c8c40f0d3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0020466901183242726,
+  "epoch": 0.004093380236648545,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 11.236,
       "eval_steps_per_second": 5.618,
       "step": 2
+    },
+    {
+      "epoch": 0.003070035177486409,
+      "grad_norm": 12.467994689941406,
+      "learning_rate": 3e-05,
+      "loss": 24.1962,
+      "step": 3
+    },
+    {
+      "epoch": 0.004093380236648545,
+      "grad_norm": 18.06902503967285,
+      "learning_rate": 4e-05,
+      "loss": 28.6901,
+      "step": 4
+    },
+    {
+      "epoch": 0.004093380236648545,
+      "eval_loss": 1.3918755054473877,
+      "eval_runtime": 393.5444,
+      "eval_samples_per_second": 4.183,
+      "eval_steps_per_second": 2.091,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2691273546792960.0,
+  "total_flos": 5382547093585920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null